© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64902
    Prev
    Next
    INDEX
    Explanations

    programming commands

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on the “.” operator in code when it’s used for member or method access (object.property or object.method).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     their
    -1.37
     any
    -1.36
     voetballer
    -1.26
     almas
    -1.26
    üte
    -1.24
     miliki
    -1.24
     materiais
    -1.23
     other
    -1.21
    isesi
    -1.20
     '\\;'
    -1.20
    POSITIVE LOGITS
     establecidos
    1.19
    He
    1.16
      
    1.11
     was
    1.08
     epics
    1.05
     spire
    1.03
    を行います
    1.00
    '
    0.99
     softshell
    0.99
    MA
    0.98
    Activations Density 0.010%

    No Known Activations